Home


github
scholar
linkedin
orcid
CV
email

I am a machine learning researcher at Imagine (A3SI/LIGM, ENPC, IP-Paris), Senior Hi!Paris Fellow, and associate researcher at IGN in the LASTIG lab. I focus on computer vision and machine elarning for geospatial analysis and environment monitoring. I work with a variety of modalities: 3D point clouds, satellites time series, historical maps, street view images, and of course massively multimodal datasets.
Area chair for 3DV2026, CVPR2025/26, ECCV2024 and IGARSS2024.

Looking for 2 interns / PhD: on geolocation and super-resolved forest analysis

NEWS


🆕 Our CVPR Workshop EarthVision is renewed for its 9th edition. Don’t miss the leading event of computer vision + Earth observation
🆕 Our paper on ultra-high resolution has been accepted at TMLR. Overall, great reviewing experience, highly recommend!
🆕 I will present my work at Meta FAIR, Google Deepmind, EPFL, ETH Zurich, EGU, INRIA LIRMM, Pioneer Centre for AI, IADF OrbitTracks, and Paris Saclay Summit
🆕 We are organizing the 1st workshop on Representation Learning for Earth Observation at Eurips 2025
🆕 Our paper on historical maps has been accepted to ICDAR2025 as an oral 🎤
🆕 4 new grants: ANR DEEPFOREST with LSCE and EFEO (666k€), senior Hi! Paris senior fellowship (360k€), DIM PAMIR with EFEO (75k€), CNES post-doc with LSCE (140k€)
🆕 👏 Congrats to my former student Damien Robert for recieving an accessit to the AFRIF PhD Award
🆕 3 papers accepted at CVPR2025: AnySat (highlight ✨), Generative Geoloc, and Open-Canopy

SELECTED ARTICLES

FORMSpoT: A Decade of Tree-Level, Country-Scale Forest Monitoringm Martin Schwartz, Fajwel Fogel, Nikola Besic, Damien Robert, Louis Geist, Jean-Pierre Renaud, Jean-Matthieu Monnet, Clemens Mosig, Cédric Vega, Alexandre d’Aspremont, Loic Landrieu, Philippe Ciais,
2025
[arxiv] [data soon!]

Adapting Vision Transformers to Ultra-High Resolution Semantic Segmentation with Relay Tokens, Yohann Perron, Vladyslav Sydorov, Christophe Pottier, Loic Landrieu,
TMLR 2025
[arxiv] [project]

Order Matters: 3D Shape Generation from Sequential VR Sketches, Yizi Chen, Sidi Wu, Tianyi Xiao, Nina Wiedemann, Loic Landrieu
2025
[arxiv] [gihub] [project]

EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation, Louis Geist, Loic Landrieu, Damien Robert.
2025
[arxiv] [project]

Segmenting France Across Four Centuries, Marta LĂłpez-Rauhut, Hongyu Zhou, Mathieu Aubry, Loic Landrieu,
ICDAR 2025 (oral 🎤, top 8%)
[arxiv] [data] [github]

AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities, Guillaume Astruc, Nicolas Gonthier, Clement Mallet, Loic Landrieu,
CVPR 2025 (highlight ✨ top 3%)
[arXiv], [project], [models],

Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation, Nicolas Dufour, David Picard, Vicky Kalogeiton, Loic Landrieu,
CVPR 2025
[arXiv], [demo], [project], [models]

Open-Canopy: Towards Very High Resolution Forest Monitoring, Fajwel Fogel, Yohann Perron, Nikola Besic, Laurent Saint-André, Agnès Pellissier-Tanon, Martin Schwartz, Thomas Boudras, Ibrahim Fayad, Alexandre d’Aspremont, Loic Landrieu, Phillipe Ciais,
CVPR 2025 (highlight ✨ top 3%)
[arXiv], [github and data]

CoDEx: Combining Domain Expertise for Spatial Generalization in Satellite Image Analysis. Abhishek Kuriyal, Elliot Vincent, Mathieu Aubry, and Loic Landrieu,
CVPR 2025 Workshop EarthVision
[arXiv], [project]

A Survey and Benchmark of Automatic Surface Reconstruction from Point Clouds Raphael Sulzer, Renaud Marlet, Bruno Vallet, Loic Landrieu,
TPAMI 2024
[arXiv], [github and data]

Archaeoscape: Bringing Aerial Laser Scanning Archaeology to the Deep Learning Era, Yohann Perron*,Vladyslav Sydorov*, Adam P. Wijker, Damian Evans, Christophe Pottier, Loic Landrieu,
NeurIPS Benchmark & Dataset 2024 (splotlight ✨ top 3%)
[paper], [github and data]

OmniSat: Self-Supervised Modality Fusion for Earth Observation, Guillaume Astruc, Nicolas Gonthier, Clément Mallet, Loic Landrieu,
ECCV 2024
[arXiv], [github and data]

OpenStreetView-5M: The Many Roads to Global Visual Geolocation, Guillaume Astruc*, Nicolas Dufour*, Ioannis Siglidis*, Constantin Aronssohn, Nacim Bouia, Stephanie Fu, Romain Loiseau, Van Nguyen Nguyen, Charles Raude, Elliot Vincent, Lintao XU, Hongyu Zhou, Loic Landrieu,
CVPR 2024.
[demo] [paper] [data] [project]

Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans, Romain Loiseau, Elliot Vincent, Mathieu Aubry, Loic Landrieu,
CVPR 2024.
[github] [arXiv] [project] [data]

StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation, Sidi Wu*, Yizi Chen*, Samuel Mermet, Lorenz Hurni, Nicolas Gonthier, Konrad Schindler, Loic Landrieu,
CVPR 2024.
[github] [arXiv] [data]

Scalable 3D Panoptic Segmentation as Superpoint Graph Clustering, Damien Robert, Hugo Raguet, Loic Landrieu,
3DV 2024 (oral 🎤 top 5%).
[github] [arXiv]

FLAIR : a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery, Anatol Garioud, Nicolas Gonthier, Loic Landrieu, Apolline De Wit, Marion Valette, Marc Poupée, Sébastien Giordano, Boris Wattrelos
NeurIPS Dataset and Benchmark 2023.
[challenge] [github] [arXiv]

Efficient 3D Semantic Segmentation with Superpoint Transformer, Damien Robert, Hugo Raguet, Loic Landrieu,
ICCV 2023.
[project] [arXiv] [github]

A Model You Can Hear: Audio Identification with Playable Prototypes, Romain Loiseau, Baptiste Bouvier, Yann Teytaut, Elliot Vincent, Mathieu Aubry, Loic Landrieu,
ISMIR 2022.
[project] [arXiv] [github]

Online Segmentation of LiDAR Sequences: Dataset and Algorithm, Romain Loiseau, Mathieu Aubry, Loic Landrieu,
ECCV 2022.
[arXiv][github] [data] [project]

Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation, Damien Robert, Bruno Vallet, Loic Landrieu,
CVPR 2022 (oral 🎤, best paper finalist 🏅top 0.4%).
[arXiv] [github]

Multi-Layer Modeling of Dense Vegetation from Aerial LiDAR Scans, Ekaterina Kalinicheva, Loic Landrieu, Clement Mallet, Nesrine Chehata,
CVPR Workshop EarthVision 2022.
[arXiv] [github]

Deep Surface Reconstruction from Point Clouds with Visibility Information. Raphael Sulzer, Loic Landrieu, Alexandre Boulch, Renaud Marlet, Bruno Vallet,
ICPR 2022.
[arXiv] [github]

Multi-Modal Temporal Attention Models for Crop Mapping from Satellite Time Series, Vivien Sainte Fare Garnot, Loic Landrieu, 
ISPRS Journal of Photogrammetry and Remote Sensing 2022.
 [arXiv] [data] [github]

Representing Shape Collections with Alignment-Aware Linear Models, Romain Loiseau, Tom Monnier, Mathieu Aubry, Loic Landrieu
3DV 2021.
[arXiv] [project] [github]


Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks, Vivien Sainte Fare Garnot, Loic Landrieu,
ICCV 2021.
[arXiv] [github] [data]

Scalable Surface Reconstruction with Delaunay-Graph Neural Networks, Raphael Sulzer, Loic Landrieu, Renaud Marlet, and Bruno Vallet,
Eurographics SGP 2021.
[arXiv] [github]

Leveraging Class Hierarchies with Metric-Guided Prototype Learning, Vivien Sainte Fare Garnot, Loic Landrieu,
BMVC 2021.
[arXiv] [github]

Torch-Points3D: A Modular Multi-Task Framework for Reproducible Deep Learning on 3D Point Clouds, Thomas Chaton, Nicolas Chaulet, Sofiane Horache, Loic Landrieu,
3DV 2020 (oral 🎤 top 10%).
[arXiv] [github]

Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention, Vivien Sainte Fare Garnot, Loic Landrieu, Sebastien Giordano, Nesrine Chehata,
CVPR 2020 (oral 🎤 top 5%).
[arXiv] [github]

Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning, Loic Landrieu, Mohamed Boussaha,
CVPR 2019.
[arXiv] [github]

Cut-Pursuit Algorithm for Regularizing Nonsmooth Functionals with Graph Total Variation, Hugo Raguet, Loic Landrieu,
ICML 2018. 
[arXiv] [github]

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs, Loic Landrieu* and Martin Simonovsky*,
CVPR 2018.
[arXiv] [github]

Cut Pursuit: Fast Algorithms to Learn Piecewise Constant Functions on General Weighted Graphs. Loic Landrieu, Guillaume Obozinski, 
SIAM Journal on Imaging Science, 2017.
[hal][github]

A Structured Regularization Framework for Spatially Smoothing Semantic Labelings of 3D Point Clouds. Loic Landrieu, Hugo Raguet , Bruno Vallet , Clément Mallet, Martin Weinmann,
ISPRS Journal of Photogrammetry and Remote Sensing, 2017.
[hal] [github]

Preconditioning of a Generalized Forward-Backward Splitting and Application to Optimization on Graphs. Hugo Raguet, Loic Landrieu,
SIAM Journal on Imaging Science, 2015.
[arxiv] [github]

COMMUNITY

- Area Chair for CVPR26, 3DV26, CVPR25, ECCV24 and IGARSS24.
- Work Package Leader for the SHARP PEPR on Frugal AI
- Co-chair of the ISPRS working group Temporal Geospatial Data Understanding
- Co-organizer of the EarthVision CVPR Workshop (2021,2022,2023,2024,2025)
- Co-organizer of the Representation Learning for Earth Observation (REO) workshop at EurIPS (2025)
- Co-Program chair of the XXIVth ISPRS congress
- Editorial Advisory Board of ISPRS Journal (Elsevier, IF:11.8) & Reviewing Committee of Remote Sensing (MDPI, IF:5.3)
- ELLIS member.

Reviewer for: ICML, NeurIPS, ICCV, ECCV, CVPR, ACCV, BMVC, IJCV, PAMI, ANRT, IJPRS, TIP, ISPRS etc...
Oustanding reviewer for: ICML21, CVPR21, ECCV22, ICCV2023, and ISPRS-Congress22, ISPRS Journal 2021 & 2022.

STUDENTS:

List of current and past PhD/Post Doc students:

List of current and past interns:
Stephane Guinard, Simon Bailly, Omar Lahbib, Joana Roussillon, Thomas Luo , Anna Kondracka, Lamiae El-Mendili, Ameur Zaibi, Julien Baconat, CĂ©dric Baron, FĂ©lix Quinton, Yaping Lin, Dina El-Zein, Hongyu Zhou, Guillaume Astruc, Jakub Vynikal, Abishek Kuriya

MISC

I teach machine learning at master level at MVA, ENSG and ENPC.

I am a technical advisor for SAMP, a startup using machine learning to produce digital twins of industrial facilities.

I offer machine learning / computer vision consulting. Notable clients include QuantCube, Helix.re, Samp.ai, Gambi-M, Eurobios Mews Labs.